Platform solves challenge of robots interacting with people and the world
27 August 2025 
Nvidia has announced a computer platform designed to power robots in applications including manufacturing, logistics, transportation, healthcare, agriculture and retail. The Jetson AGX Thor developer kit and production modules deliver 7.5 times more AI computing power, 3.5 times better energy efficiency and twice as much memory as its predecessor, the Jetson Orin platform, unlocking real-time reasoning, which is critical for high-performance physical AI applications.
The new system-on-module platform is claimed to solve one of the most biggest challenges in robotics: running multi-AI workflows, thus allowing robots to have real-time, intelligent interactions with people and the physical world.
Early adopters of the new platform include Agility Robotics, Amazon Robotics, Boston Dynamics, Caterpillar, Figure and Hexagon. John Deere, OpenAI and Physical Intelligence are evaluating the technology to advance their physical AI capabilities.
“We’ve built Jetson Thor for the millions of developers working on robotic systems that interact with and increasingly shape the physical world,” says Nvidia’s founder and CEO, Jensen Huang. “With unmatched performance and energy efficiency, and the ability to run multiple generative AI models at the edge, Jetson Thor is the ultimate supercomputer to drive the age of physical AI and general robotics.”
Since Nvidia launched the Jetson platform and robotics stack in 2014, more than two million developers, and an ecosystem of more than 150 hardware, software and sensor partners, have adopted the technology, allowing more than 7,000 customers to use edge AI in a variety of industries. The new platform pushes the frontier further for visual AI agents and complex robotic systems such as humanoids and surgical robots.
Powered by an Nvidia’s Blackwell GPU and offering 128GB of memory, Jetson Thor delivers up to 2,070 FP4 teraflops of AI computing power to run the latest AI models, requiring a maxium 130W of power. A developer kit is available now with prices from $3,499.
Brett Adcock, founder and CEO of the US humanoid robot developer, Figure, says that development of capable humanoids “hinges on our ability to run powerful AI models directly on the robot, enabling real-time learning and interaction. Nvidia Jetson Thor’s server-class performance, delivered within a compact and power-efficient design, allows us to deploy the large-scale generative AI models necessary for our humanoids to perceive, reason and act in complex, unstructured environments.”
“The future of robotics in logistics depends on the ability to deploy increasingly intelligent and autonomous systems,” adds Tye Brady, chief technologist at Amazon Robotics. “Nvidia Jetson Thor offers the computational horsepower and energy efficiency necessary to develop and scale the next generation of AI-powered robots that can operate safely and effectively in dynamic, real-world environments, transforming how we move and manage goods globally.”
The German semiconductor developer Infineon has announced that it will be using Nivia’s new platform with its own microcontrollers, sensors and actuators to enable OEMs to create more efficient powerful and scalable motor control systems for humanoid robots. Infineon’s PSOC Control microcontrollers implement FOC (field-oriented control) algorithms that can reduce motor noise and provide stable torque outputs to curb vibrations in humanoid and other applications.
Boston Dynamics is integrating Jetson Thor into its Atlas humanoid robot, giving it the computing power that previously required servers, as well as accelerating its AI workload, extending its data-processing bandwidth and adding significant on-device memory.
Another US humanoid developer, Agility Robotics, plans to adopt Jetson Thor as the onboard computing platform for the sixth generation of its Digit logistics robot, enhancing its real-time perception and decision-making capabilities, and supporting increasingly complex AI skills and behaviours. Digit performs tasks such as stacking, loading and palletising in warehouse and manufacturing environments.
The processing power offered by the new platform “will take Digit to the next level, enhancing its real-time responsiveness and expanding its abilities to a broader, more complex set of skills,” says Agility’s CEO, Peggy Johnson. “With Jetson Thor, we can deliver the latest physical AI advancements to optimize operations across our customers’ warehouses and factories.”
